Loading...
Loading...
Found 78 Skills
Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
Break an approved spec into ordered implementation tasks with dependencies, sequencing logic, and done criteria.
Use when you have specs or requirements for a multi-step task to break it down into detailed tasks, before executing it
Help neurodivergent users break down overwhelming tasks into manageable steps. Use when tasks feel paralyzing, when executive function is struggling, when someone can't start, or when the Wall of Awful has built up. Applies ADHD/autism-aware decomposition strategies.
This skill should be used when the user asks to "break down tasks", "create a task list", "plan implementation", "decompose architecture", "create agent tasks", "plan MVP build", "break down feature", "create execution plan", or mentions task breakdown, agent development workflow, or implementation planning. Two-phase workflow for AI agent development with granular, testable tasks.
Convert technical designs into actionable, sequenced implementation tasks. Create clear coding tasks that enable incremental progress, respect dependencies, and provide a roadmap for systematic feature development.
Use when a feature touches 4 or more files, involves multiple components, or has subtasks that could run in parallel.
Break an implementation plan markdown file into a sequenced, dependency-annotated, checkbox-tracked task list saved as a sibling doc (e.g. `docs/<feature>-tasks.md`). Each task is annotated with the lower-numbered tasks it depends on (or marked dependency-free) and ordered topologically, so independent tasks can be implemented in parallel. The task list is the execution contract — each task is one logical commit that bundles the code change **and** the ticked checkbox together (never a separate "tick-only" commit). Use this whenever the user has an implementation plan (file like `docs/<thing>-plan.md`, an `## Implementation plan` section, or a freshly written design doc) and wants a step-by-step todo list to drive the build. Trigger on phrases like "break this plan into tasks", "make a task list", "generate the tasks doc", "turn this plan into checkboxes", "split this into steps I can implement one by one", or whenever a plan exists and the next move is execution — even if the user doesn't explicitly say "task list".
Decomposes a spec or architecture into buildable tasks with acceptance criteria, dependencies, and implementation order for AI agents or engineers. Produces `.agents/tasks.md`. Not for clarifying unclear requirements (use discover) or designing architecture (use system-architecture). For code quality checks after building, see review-chain. For packaging and PRs, see ship.
Turn a settled business-logic spec (from `feature-discovery` or a freshly-described feature in chat) into a detailed, code-grounded implementation plan saved as `docs/<feature-slug>-plan.md`, ready for `plan-task-breakdown` to convert into checkboxes. Verifies feasibility against the actual codebase, names the specific files/types/actions/components to touch, identifies test cases at every layer that fits (unit, integration, and — for user-visible flows — a Playwright happy-path e2e test), and asks the user clarifying questions for implementation-level ambiguities only — never re-litigates business logic. Use this skill whenever a feature's *what* is clear and the next move is mapping it to *how*. Trigger on phrases like "make a plan", "write the implementation plan", "plan this out", "design the build", "turn this spec into a plan", "how would we implement this", "scope out how to build X", "draft a plan for <feature>", or whenever the conversation just produced a business spec and the natural next step is implementation design — even if the user doesn't say "implementation plan" explicitly.
Conversational discovery — adapts from quick scoping (3-5 questions) to deep interviews (multi-round). Talk until we're clear, then build. Produces inline decisions; optionally saves spec.md or scope contract. Not for multi-perspective debate (use agent-room). Not for decomposing work (use task-breakdown).
Multi-agent discussion rooms — debate or poll a problem from multiple perspectives. Standalone or invoked by other skills as a sub-routine. Mode=debate: N agents argue in rounds, converge. Mode=poll: N agents independently analyze, aggregate by consensus. Not for implementation (use system-architecture). Not for verification (use review-chain). For clarifying requirements first, see discover. For decomposing work after a decision, see task-breakdown.